I have been doing a bunch of experiments with the latest vision models and PDFs recently, they're pretty great! Claude 3 Opis did point-blank refuse to answer questions about one that included personally identifiable information though
PROMPT ENGINEERING
-
Effective Chunking Strategies for GPT-3.5 Implementation
By
–
Have you found a chunking strategy that works well powered by gpt-3.5? I am hoping to add chunking to LLM at some point but I'm not sure what strategies I should include
-
LangChain Explained: Agents, Prompts, and Retrievers Overview
By
–
What is LangChain? via IBM There are a lot of concepts in LangChain (agents, prompts, retrievers, etc) This is a great conceptual video (no code) from IBM on how all these pieces fit together https://
youtube.com/watch?v=1bUy-1
hGZpI
… -
New LLM Primer Book Offers Practical Usage Tips
By
–
My friend @emollick assesses large language models as deeply as anyone, and his primer book, coming out this week, is chock full of useful tips for how to use them. And I love the title.
-
OCR Tool Built with Claude 3 Opus and GPT-4
By
–
Try it out here: https://
tools.simonwillison.net/ocr I wrote about how I built it – including all of the prompts I used through both Claude 3 Opus and a little bit of ChatGPT/GPT-4 – on my blog: -
AI System Generates Multiple Images with Contextual Text
By
–
It also works with multiple images!
— Pietro Schirano (@skirano) 30 mars 2024
Just ask how many you want, and it'll figure out the rest, even writing an appropriate paragraph based on the images. https://t.co/Ctjp2hPVYj pic.twitter.com/GDRcUvjYLxIt also works with multiple images! Just ask how many you want, and it'll figure out the rest, even writing an appropriate paragraph based on the images.
-
Long-context models will enable brute force approaches
By
–
Short term, it’s still useful. Long-term, yeah, I think better + cheaper long-context models will lead to brute forcing being the right approach
-
How Claude 3 and GPT-4 simplified AI prompt engineering
By
–
All you new AI engineers don’t know how easy you have it. With Claude 3/GPT-4, you can write a lazy prompt in one try and it’ll still perform pretty well. Back in the day, you had to spend hours, if not days, carefully iterating GPT-3 prompts to make things work.
-
Claude 3 Prompt for Code Refactoring and Engineering Optimization
By
–
Here is a powerful Claude 3 prompt for engineers. Use it to automatically refactor, comment, and improve your code: — You are a skilled software engineer with deep expertise in code refactoring and optimization across multiple programming languages. Your
-
Math Application with LangChain Agents and LLMs
By
–
Building a Math Application with LangChain Agents A tutorial on why LLMs struggle with math, and how to resolve these limitations using LangChain Agents, OpenAI and Chainlit Can easily be extended to augmenting LLMs with other tools!